Artículo
Cross-domain polarity classification using a knowledge-enhanced meta-classifier
Autor/es | Franco Salvador, Marc
Cruz Mata, Fermín Troyano Jiménez, José Antonio Rosso, Paolo |
Departamento | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos |
Fecha de publicación | 2015 |
Fecha de depósito | 2020-07-18 |
Publicado en |
|
Resumen | Current approaches to single and cross-domain polarity classification usually use bag of words, n-grams
or lexical resource-based classifiers. In this paper, we propose the use of meta-learning to combine and
enrich those ... Current approaches to single and cross-domain polarity classification usually use bag of words, n-grams or lexical resource-based classifiers. In this paper, we propose the use of meta-learning to combine and enrich those approaches by adding also other knowledge-based features. In addition to the aforementioned classical approaches, our system uses the BabelNet multilingual semantic network to generate features derived from word sense disambiguation and vocabulary expansion. Experimental results show state-of-the-art performance on single and cross-domain polarity classification. Contrary to other approaches, ours is generic. These results were obtained without any domain adaptation technique. Moreover, the use of meta-learning allows our approach to obtain the most stable results across domains. Finally, our empirical analysis provides interesting insights on the use of semantic network-based features. |
Agencias financiadoras | European Commission (EC) Ministerio de Economía y Competitividad (MINECO). España Ministerio de Economía y Competitividad (MINECO). España Junta de Andalucía |
Identificador del proyecto | WIQ-EI IRSES (No. 269180)
TIN2012-38603-C02-01 TIN2012-38536-C03-02 P11-TIC-7684 MO |
Cita | Franco Salvador, M., Cruz Mata, F., Troyano Jiménez, J.A. y Rosso, P. (2015). Cross-domain polarity classification using a knowledge-enhanced meta-classifier. Knowledge-Based Systems, 86 (september 2015), 45-56. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Cross-domain polarity.pdf | 415.0Kb | [PDF] | Ver/ | |